• State Resolved
  • Locked Locked
  • Replies 1 reply
  • Subscribers 98 subscribers
  • Views 209 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

SK-TDA4VM: How to get the output of the neural network?

Cherry Zhou
Mastermind 22235 points
Part Number: SK-TDA4VM

Hi team,

SK-TDA4VM AI BASE SDK 08_06_00 version is being used.

When running TI's Edge AI demo, how to get deep learning test results? The customer run object detection using the rpiV2 camera and when running the CPP routine, only the test box is output in the image of output. In the customer's project, it is required to have the information output, such as the center of the test box. 

The customer guess that the test box drawing of the original image should be implemented in post-proc, etc., but how to get the output of the specific test case here? 

Could you help check this case? Thanks.

Best Regards,

Cherry

  • +1
    TI__Mastermind 24041 points

    Hi,

    As per you posted question, could you please try to elaborate what is exact issue you are facing ?

    My understanding after comprehending the posted question is, you are running object detection demo using SK-TDA4VM on linux sdk 08.06.

    You want to print information about bounding box centers when the inference is running ? 

    Cherry Zhou said:
    The customer guess that the test box drawing of the original image should be implemented in post-proc, etc.,

    Yes, the bounding boxes are the part of post processing, the model outputs the bounding box co-ordinates for the same.

    Regards,

    Pratik